martimfasantos
commited on
Commit
•
9ffcd30
1
Parent(s):
65e92ac
Model save
Browse files- README.md +7 -8
- adapter_model.safetensors +1 -1
- all_results.json +4 -9
- runs/May05_22-31-16_poseidon/events.out.tfevents.1714948312.poseidon.1517230.0 +2 -2
- train_results.json +4 -4
- trainer_state.json +0 -0
README.md
CHANGED
@@ -2,13 +2,12 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
10 |
datasets:
|
11 |
-
-
|
12 |
model-index:
|
13 |
- name: tinyllama-1.1b-sum-sft-qlora
|
14 |
results: []
|
@@ -19,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
# tinyllama-1.1b-sum-sft-qlora
|
21 |
|
22 |
-
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 2.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -54,10 +53,10 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
-
| Training Loss | Epoch | Step
|
58 |
-
|
59 |
-
| 2.
|
60 |
-
| 2.
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
9 |
datasets:
|
10 |
+
- generator
|
11 |
model-index:
|
12 |
- name: tinyllama-1.1b-sum-sft-qlora
|
13 |
results: []
|
|
|
18 |
|
19 |
# tinyllama-1.1b-sum-sft-qlora
|
20 |
|
21 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.1271
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 2.1288 | 1.0 | 2952 | 2.1320 |
|
59 |
+
| 2.1251 | 2.0 | 5904 | 2.1271 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25272360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8076beadd85c592661edeaa3a4a760b37a9bb64dd0b27f7196eea862943c4fd
|
3 |
size 25272360
|
all_results.json
CHANGED
@@ -1,13 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"eval_samples": 6553,
|
6 |
-
"eval_samples_per_second": 16.441,
|
7 |
-
"eval_steps_per_second": 2.061,
|
8 |
-
"train_loss": 2.1527459967507903,
|
9 |
-
"train_runtime": 22011.903,
|
10 |
"train_samples": 116722,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"train_loss": 2.1395560028107186,
|
4 |
+
"train_runtime": 20794.4522,
|
|
|
|
|
|
|
|
|
|
|
5 |
"train_samples": 116722,
|
6 |
+
"train_samples_per_second": 2.272,
|
7 |
+
"train_steps_per_second": 0.284
|
8 |
}
|
runs/May05_22-31-16_poseidon/events.out.tfevents.1714948312.poseidon.1517230.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7e604a60587c6ed8959710fab8f414101a5ed23aa3acabfd8ddf4b44b7ccfb2
|
3 |
+
size 255267
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
-
"train_loss": 2.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 116722,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"train_loss": 2.1395560028107186,
|
4 |
+
"train_runtime": 20794.4522,
|
5 |
"train_samples": 116722,
|
6 |
+
"train_samples_per_second": 2.272,
|
7 |
+
"train_steps_per_second": 0.284
|
8 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|